An efficient chain code based face identification system for biometrics

Presently, face detection has become an important aspect in biometric identification systems. Among many other facial features like position of nose, lips, eye, face contour acts as an important classifier in face detection. It requires huge memory space to store reference images of face in face recognition. Thus memory space can be optimized if the contour of a face is stored instead of complete image of the face. In this paper we propose a face identification methodology where contour of a face is encoded by chain codes and the database is formed and an algorithm has been developed for face recognition. Further, a complexity analysis has been done in both time and space aspects, and have been found more efficient than conventional template matching methods in face detection.